Perceptual QoE-Optimal Resource Allocation for Adaptive Video Streaming

Kuchi, Kiran and Kumar, Abhinav and Channappayya, Sumohana and et al, . (2020) Perceptual QoE-Optimal Resource Allocation for Adaptive Video Streaming. IEEE Transactions on Broadcasting, 66 (2). pp. 1-13. ISSN 0018-9316

[img] Text
Perceptual_QoE-Optimal_Resource_Allocation_for_Adaptive_Video_Streaming.pdf - Published Version
Available under License Creative Commons Attribution.

Download (1MB)


Video streaming in mobile environments has always been challenging due to various factors. The time-varying wireless channel, limited and shared transmission resources, fluctuating network conditions between the video server and the end user etc. greatly affect the timely delivery of videos. Given these factors, it is important that the wireless networks perform optimal allocation of resources and cater to the demands of the video streaming users without degrading their quality-of-experience (QoE). Modeling streaming QoE as perceived subjectively by the users is non-trivial, and in general a complex task, as it is continuous, dynamic, and time-varying in nature. The continuous perceptual QoE degradation due to network induced artifacts such as time-varying video quality and rebuffering events has not been considered in the literature for resource allocation (RA). In this paper, we propose Video Quality Aware Resource Allocation (ViQARA), a perceptual QoE based RA algorithm for video streaming in cellular networks. ViQARA leverages the strength of the latest continuous QoE models and integrates it with the generalized α-fair strategy for RA. Through extensive simulations, we demonstrate that ViQARA can provide significant improvement in the users perceptual QoE as well as a remarkable reduction in the number of rebufferings when compared to existing throughput based RA methods. The proposed algorithm is also shown to provide better QoE optimization of the available resources in general, and especially so when the cellular network is resource constrained and/or experiences large packet delays.

[error in script]
IITH Creators:
IITH CreatorsORCiD
Kuchi, Kiran0000-0002-5880-4023
Kumar, Abhinav0000-0002-6468-7054
Channappayya, Sumohana0000-0002-5687-0887
Item Type: Article
Additional Information: This work was supported by the Intel India Ph.D. Fellowship, Intel Corporation.
Uncontrolled Keywords: α-fairness, DASH, machine learning, NARX, QoE, rebuffering, resource allocation, SVR, time-varying quality, video streaming
Subjects: Electrical Engineering
Divisions: Department of Electrical Engineering
Depositing User: Team Library
Date Deposited: 24 Dec 2019 06:26
Last Modified: 15 Nov 2022 10:04
Publisher URL:
OA policy:
Related URLs:

Actions (login required)

View Item View Item
Statistics for RAIITH ePrint 7236 Statistics for this ePrint Item